Discover Awesome MCP Servers
Extend your agent with 84,517 capabilities via MCP servers.
- All84,517
- Developer Tools3,867
- Search1,714
- Research & Data1,557
- AI Integration Systems229
- Cloud Platforms219
- Data & App Analysis181
- Database Interaction177
- Remote Shell Execution165
- Browser Automation147
- Databases145
- Communication137
- AI Content Generation127
- OS Automation120
- Programming Docs Access109
- Content Fetching108
- Note Taking97
- File Systems96
- Version Control93
- Finance91
- Knowledge & Memory90
- Monitoring79
- Security71
- Image & Video Processing69
- Digital Note Management66
- AI Memory Systems62
- Advanced AI Reasoning59
- Git Management Tools58
- Cloud Storage51
- Entertainment & Media43
- Virtualization42
- Location Services35
- Web Automation & Stealth32
- Media Content Processing32
- Calendar Management26
- Ecommerce & Retail18
- Speech Processing18
- Customer Data Platforms16
- Travel & Transportation14
- Education & Learning Tools13
- Home Automation & IoT13
- Web Search Integration12
- Health & Wellness10
- Customer Support10
- Marketing9
- Games & Gamification8
- Google Cloud Integrations7
- Art & Culture4
- Language Translation3
- Legal & Compliance2
big-mcp-b3
MCP server for B3 (Brazilian stock exchange) data, offering tools for real-time quotes, historical prices, dividends, FIIs, fundamental analysis, options, and indices via natural language.
MCP Registry Server
Enables searching and retrieving detailed information about MCP servers from the official MCP registry. Provides tools to list servers with filtering options and get comprehensive details about specific servers.
Simple MCP Server
Claro, aqui está um exemplo minimalista de como construir um servidor MCP (Meta Configuration Protocol) em Python, usando a biblioteca `asyncio`: ```python import asyncio import json async def handle_client(reader, writer): """Lida com a conexão de um cliente.""" addr = writer.get_extra_info('peername') print(f"Conectado com {addr}") try: while True: data = await reader.readline() if not data: break message = data.decode().strip() print(f"Recebido de {addr}: {message}") try: # Tenta analisar a mensagem como JSON (formato comum para MCP) request = json.loads(message) # Lógica básica de exemplo: ecoa a requisição de volta response = {"status": "ok", "request_received": request} response_json = json.dumps(response) + "\n" # Adiciona newline para delimitar a mensagem writer.write(response_json.encode()) await writer.drain() # Garante que os dados sejam enviados print(f"Enviado para {addr}: {response_json.strip()}") except json.JSONDecodeError: error_message = "Erro: Requisição JSON inválida\n" writer.write(error_message.encode()) await writer.drain() print(f"Enviado para {addr}: {error_message.strip()}") except Exception as e: print(f"Erro ao lidar com {addr}: {e}") finally: print(f"Fechando conexão com {addr}") writer.close() await writer.wait_closed() async def main(): """Função principal para iniciar o servidor.""" server = await asyncio.start_server( handle_client, '127.0.0.1', 8888 # Escuta em localhost na porta 8888 ) addr = server.sockets[0].getsockname() print(f"Servindo em {addr}") async with server: await server.serve_forever() if __name__ == "__main__": asyncio.run(main()) ``` **Explicação:** 1. **`handle_client(reader, writer)`:** - Esta função lida com cada conexão de cliente individualmente. - `reader` e `writer` são objetos `StreamReader` e `StreamWriter` do `asyncio`, usados para ler e escrever dados na conexão. - Ela lê linhas do cliente (`reader.readline()`), decodifica para string, e tenta analisar como JSON. - Se a análise JSON for bem-sucedida, ela cria uma resposta JSON (neste exemplo, apenas ecoa a requisição) e envia de volta ao cliente. - Se houver um erro de análise JSON, ela envia uma mensagem de erro. - A função usa `await writer.drain()` para garantir que os dados sejam realmente enviados antes de continuar. - Ela também lida com erros e fecha a conexão quando terminada. 2. **`main()`:** - Esta função é a função principal que inicia o servidor. - `asyncio.start_server()` cria um servidor que escuta em um endereço e porta especificados (neste caso, localhost na porta 8888). - `handle_client` é a função de *callback* que será chamada para cada nova conexão de cliente. - `server.serve_forever()` mantém o servidor rodando indefinidamente, aceitando novas conexões. 3. **Formato JSON:** - O exemplo usa JSON como um formato comum para mensagens MCP. MCP geralmente envolve troca de dados estruturados, e JSON é uma maneira popular de representar esses dados. **Como executar:** 1. Salve o código como um arquivo Python (por exemplo, `mcp_server.py`). 2. Execute o arquivo no terminal: `python mcp_server.py` 3. O servidor estará rodando em `127.0.0.1:8888`. **Como testar:** Você pode usar `telnet`, `netcat` ou um cliente HTTP (como `curl` ou `Postman`) para enviar requisições JSON para o servidor. Aqui está um exemplo usando `netcat`: ```bash echo '{"command": "get_config", "key": "my_setting"}' | nc 127.0.0.1 8888 ``` Você deverá ver a resposta do servidor no terminal do servidor e no terminal do cliente. **Observações:** * **Minimalista:** Este é um exemplo muito básico. Um servidor MCP real seria muito mais complexo, com lógica para lidar com diferentes tipos de requisições, autenticação, autorização, etc. * **Tratamento de Erros:** O tratamento de erros é básico. Em um servidor de produção, você precisaria de um tratamento de erros mais robusto. * **Concorrência:** `asyncio` permite que o servidor lide com múltiplas conexões simultaneamente de forma eficiente. * **Formato MCP:** O formato exato das mensagens MCP pode variar dependendo da implementação específica. Este exemplo usa JSON, mas outros formatos (como Protocol Buffers) também podem ser usados. * **Delimitação de Mensagens:** A adição de `\n` (newline) no final da mensagem JSON é importante para que o cliente saiba onde termina a mensagem. `reader.readline()` lê até encontrar um newline. Este exemplo fornece um ponto de partida para construir um servidor MCP mais completo. Você precisará adaptar a lógica de `handle_client` para lidar com as requisições específicas que seu servidor precisa suportar.
MCPServer
Social Media Analytics
Social media analytics toolkit that analyzes profiles, scores engagement, detects trending topics, researches hashtags, generates content calendars, and benchmarks against competitors. 6 tools across all major platforms.
K8s AI Assistant MCP Server
Enables AI-powered Kubernetes management using natural language, supporting kubectl, Helm, diagnostics, and port forwarding via MCP protocol.
mcp-knowledge-server
A production-grade RAG server with a centralized knowledge base, offering both MCP and REST APIs for semantic search, document ingestion, and RAG-based answers.
V.I.S.O.R.
Smart MCP server that reads your code, understands file connections, and provides precise context to AI coding assistants, reducing token usage and preventing errors from outdated or irrelevant files.
Simple Python MCP Server
A simple MCP server implementation in Python using FastMCP and FastAPI, providing streamable HTTP transport with optional OAuth authorization for tools like echo and math.
Security Scanner MCP Server
Enables comprehensive security scanning of code repositories to detect secrets, vulnerabilities, dependency issues, and configuration problems. Provides real-time security checks and best practice recommendations to help developers identify and prevent security issues.
self-healing-browser-mcp
Enables AI agents to control a browser with self-healing locators that automatically recover when selectors change, allowing reliable web automation through natural language.
mcp-reunion
MCP server providing 96 tools across 21 modules for La Réunion (French overseas region) open data: economy, demographics, geography, transport, health, education, elections, tourism, housing, and environment. Powered by data.regionreunion.com and data.gouv.fr.
aiowhitebit-mcp
MCP server for WhiteBit cryptocurrency exchange API, enabling market data retrieval, order book access, and real-time WebSocket streams.
SeniorCare MCP
This MCP server enables medicine management, stock/refill estimation, doctor search and availability checks, and appointment management for senior care scenarios.
ib-async-mcp
An MCP server that provides an interface for the Interactive Brokers API via the ib_async library. It enables users to manage accounts, access real-time and historical market data, and execute or monitor trades through TWS or IB Gateway.
aws-mcp-connector
Talk to AWS CLI from an MCP-speaking agent. Run any aws <service> <operation> command through the Model Context Protocol, with read-only defaults and gated write access.
MCP Holyrics
Enables control and automation of Holyrics presentation software through natural language commands for managing lyrics, media, schedules, and events. It provides specialized tools to search content and orchestrate church presentation workflows via the Holyrics API.
ap2-iso20022
Bridges AP2 and x402 payment mandates into ISO 20022 pain.001/pacs.008 records with spending-cap, expiry and authorisation guardrails, via an MCP server.
C++ Graph-RAG MCP Server
A Model Context Protocol server for analyzing large C++ codebases with semantic search, crash dump analysis, and a web UI for configuration.
Oura Ring MCP Server
A Model Context Protocol server that provides access to Oura Ring health and fitness data through the Oura API v2, enabling retrieval of sleep, activity, readiness, and other health metrics.
GBrain for BOS
This MCP server provides a cost-optimized personal-knowledge brain, enabling AI agents to query imported documents via hybrid search and synthesis at minimal monthly spend.
dbt-doctor
AI-driven MCP server that audits, profiles, detects schema drift, and auto-generates documentation for dbt projects, enabling natural language interaction with your dbt project's health.
mcp-pokemon
Enables querying Pokémon data from PokéAPI, including stats, types, abilities, evolution chains, and type matchups, via natural language or direct tool calls.
ImHex MCP Integration
Enables AI assistants to perform autonomous binary analysis, malware inspection, firmware analysis, and reverse engineering workflows through a production-ready Python MCP server connected to the ImHex hex editor.
agent-link
Enables two coding agents on separate machines to communicate directly via a private git repo, with end-to-end encryption and no server required. Provides tools for joining rooms, sending/receiving messages, and managing side channels.
Drizz Voice Generator
Enables text-to-speech audio generation using ElevenLabs voices directly from Claude conversations, supporting single and batch conversion, voice listing, and voice ID lookup.
agentkit-mesh
Enables agent-to-agent discovery and delegation via MCP, with tools for registering agents, discovering them by keyword matching, and delegating tasks over HTTP.
memser
Provides MCP agents with persistent memory operations (store, recall, forget, consolidate, list) backed by Redis, Postgres, and pgvector, including semantic search and background consolidation.
CAD MCP Server
Enables reading, analyzing, and editing CAD files (DXF and DWG) via natural language, including entity queries, layer management, and safe copy-based edits.
Bridge MCP
A Model Context Protocol server that gives any AI full control over a Windows PC, enabling application control, mouse/keyboard automation, screen capture, browser automation, and more.